---

Developing Data Products - Week 3 Assignment Introduction This project was created as part of the Developing Data Products course of the Coursera Data Science Specialisation.

The goal of the project is to create a web page presentation using R Markdown that features a plot created with Plotly, and to host the resulting web page on either GitHub Pages, RPubs, or NeoCities.

The interactive plot on the next slide represents the number of road accidents in Great Britain from 2005 to 2015, grouped by severity (slight, serious, or fatal).

knitr::opts_chunk$set(echo = TRUE, cache = TRUE)

rm(list=ls())
library(plotly)

## Loading required package: ggplot2

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

library(data.table)

## Warning: package 'data.table' was built under R version 3.5.2

library(tidyr)
library(lubridate)

## 
## Attaching package: 'lubridate'

## The following objects are masked from 'package:data.table':
## 
##     hour, isoweek, mday, minute, month, quarter, second, wday,
##     week, yday, year

## The following object is masked from 'package:base':
## 
##     date

library(zoo)

## 
## Attaching package: 'zoo'

## The following objects are masked from 'package:base':
## 
##     as.Date, as.Date.numeric

Extractdata

library(readr)
accidents0514 <- read_csv("~/Desktop/Coursera/Developing Data Products/Stats19_Data_2005-2014/Accidents0514.csv")

## Parsed with column specification:
## cols(
##   .default = col_integer(),
##   Accident_Index = col_character(),
##   Longitude = col_double(),
##   Latitude = col_double(),
##   Date = col_character(),
##   Time = col_time(format = ""),
##   `Local_Authority_(Highway)` = col_character(),
##   LSOA_of_Accident_Location = col_character()
## )

## See spec(...) for full column specifications.

accidents0514 <- accidents0514 %>%
    select(Accident_Severity, Date)

accidents15 <- read_csv("~/Desktop/Coursera/Developing Data Products/Stats19_Data_2005-2014/Accidents0514.csv")

## Parsed with column specification:
## cols(
##   .default = col_integer(),
##   Accident_Index = col_character(),
##   Longitude = col_double(),
##   Latitude = col_double(),
##   Date = col_character(),
##   Time = col_time(format = ""),
##   `Local_Authority_(Highway)` = col_character(),
##   LSOA_of_Accident_Location = col_character()
## )

## See spec(...) for full column specifications.

accidents15 <- accidents15 %>%
    select(Accident_Severity, Date)
    
    
# concatenate data tables and free up environment
accidents <- rbind(accidents0514, accidents15)
rm(list = c("accidents0514", "accidents15"))

# convert severity to factor and add labels
accidents$Accident_Severity <- factor(accidents$Accident_Severity, levels = 1:3, labels = c("Fatal", "Serious", "Slight"))

# convert date strings to Date objects
accidents$Date <- dmy(accidents$Date)

# group data by date and severity, get count, one row per date
accident_count <- accidents %>%
    group_by(Date, Accident_Severity) %>%
    summarise(count = n()) %>%
    spread(key = Accident_Severity, value = count) %>% 
    as.data.frame()

# create a smoother for each severity to visualise general trends
loess_slight <- loess(Slight ~ as.numeric(Date), data = accident_count)
loess_serious <- loess(Serious ~ as.numeric(Date), data = accident_count)
loess_fatal <- loess(Fatal ~ as.numeric(Date), data = accident_count)

Road accidents in Great Britain (2005-2015)

# plot data
plot_ly(accident_count) %>%
    add_trace(x = ~Date, y = ~Slight, type="scatter", mode = "markers", 
              name = "slight", legendgroup = "slight", 
              marker = list(color = "#52A9BD")) %>%
    add_trace(x = ~Date, y = ~Serious, type="scatter", mode = "markers",
              name = "serious", legendgroup = "serious", 
              marker = list(color = "#FFF16B")) %>%
    add_trace(x = ~Date, y = ~Fatal, type="scatter", mode = "markers",
              name = "fatal", legendgroup = "fatal", 
              marker = list(color = "#F5677D")) %>%
    add_trace(x = as.Date(loess_slight$x), y = fitted(loess_slight),
              type="scatter", mode = "lines",
              line = list(color = '#1A7A90'), 
              name = "slight Loess smoother", legendgroup = "slight", 
              hoverinfo = 'none', showlegend = FALSE) %>%
    add_trace(x = as.Date(loess_serious$x), y = fitted(loess_serious),
              type="scatter", mode = "lines",
              line = list(color = '#E9D625'),
              name = "serious Loess smoother", legendgroup = "serious",
              hoverinfo = 'none', showlegend = FALSE) %>%
    add_lines(x = as.Date(loess_fatal$x), y = fitted(loess_fatal),
              type="scatter", mode = "lines",
              line = list(color = '#DC2340'),
              name = "fatal Loess smoother", legendgroup = "fatal",
              hoverinfo = 'none', showlegend = FALSE) %>%
    layout(xaxis = list(title = "Year"),
           yaxis = list(title = "Number of Accidents")
    )

## Warning: Ignoring 35 observations